AI Is Funny - a Generative Joke Model 211
RemyBR writes "Can computers tell a good joke? Is comedy just a matter of statistics or is there something only a human can bring to creating a joke? A joke generator created at the University of Edinburgh (PDF) suggests that AI can be funny. Some AI generated jokes: 'I like my relationships like I like my source, open,' 'I like my coffee like I like my war, cold,' 'I like my boys like I like my sectors, bad.'"
Manually Generated (Score:3, Funny)
Loop detected, aborting.
Re: (Score:2)
In Soviet Russia joke laughs at YOU!
Re: (Score:3)
I have an In Soviet Russia joke generator:
> In America, you laugh at jokes.
In Soviet Russia, jokes laugh at YOU!
http://subbot.org/isragent/isragent.txt [subbot.org]
It uses the link agent ( http://subbot.org/link/ [subbot.org] ) to parse input into Subject, Verb, and Object, then moves the Object to the Subject position and adds YOU! at the end. It also tries to do some verb agreement.
Re: (Score:3)
Expert TeXpert choking smokers
Don't you think the Putin laughs at you?
See how they smile like pigs in a sty
See how they spied
I'm crying
Re:Manually Generated (Score:5, Funny)
Slashdot would be more like:
I like my slashdot like I like my cat. Hairy.
I like my slashdot like I like my cat. Hairy.
I like my slashdot like I like my cat. Hairy.
[dup...]
With the occasional interspersed 3 page rant about something nobody can make sense of
Re:Manually Generated (Score:5, Funny)
Slashdot would be more like:
I like my slashdot like I like my cat. Hairy.
I like my slashdot like I like my cat. Hairy.
I like my slashdot like I like my cat. Hairy.
[dup...]
With the occasional interspersed 3 page rant about HOSTS files
fixed that for you
Re:Manually Generated (Score:5, Funny)
Al? (Score:5, Funny)
Am I the only one who read the headline and thought of Al Gore?
ob. joke.. I like my coffee like my men - strong and black.
Re:Al? (Score:5, Funny)
Hot and sweet at first, then increasingly cold and bitter.
Re: (Score:3)
Coffee is like a woman.
Hot and sweet at first, then increasingly cold and bitter.
Sign: Don't make fun of our Coffee - Some day you'll be old and bitter, too.
Re: (Score:2)
Cue Tom Waits' "Warm beer, cold women".
Re: Al? (Score:3)
Re: (Score:3, Funny)
Coffee is like a woman.
Expensive Coffee is like an Expensive Woman .... passed by an Asian Palm Civet ... wait, that didn't quite work.
Re: (Score:2)
I like my coffee like I like my women.
Dark and bitter.
Re:Al? (Score:5, Funny)
Re: (Score:2)
Re:Al? (Score:5, Funny)
Re: (Score:2)
Re:Al? (Score:4, Funny)
Re: (Score:3)
What kind of monster mixes whiskey and coke???
Re: (Score:2)
Re: (Score:2)
A person who's drinking really crappy whiskey and doesn't want to taste the methanol.
Now now... Canadian Club has it's place in the world. CC rye and coke is the only rye it tastes good with though. Even Crown deserves to be left alone.
Re: (Score:3)
You saw they "e" in whiskey didn't you? That means American whiskey, which mostly needs a mixer to make it palatable. Canadian whisky is tolerable, even without mixers. Scotch and Irish whisky are too good to mix and must be drunk neat -- although with ice or even a little water is OK if you want something less strong.
There are a few distillers making single malts: Balcones in Texas, Stranahan's in Colorado, McCarthy's in Oregon, St. George in California, Leviathan, which I think is also from California,
Re: (Score:2)
Your coffee leaves with the toilet seat up?
Re: (Score:2)
I like my women like I like my coffee - With two lumps
Re: (Score:2)
Am I the only one who read the headline and thought of Al Gore?
Nope. My first thought was AlGore funny? Maybe the world really is coming to an end.
Re: (Score:2)
In that case, the world ended a while ago:
http://www.npr.org/2013/04/20/177981747/al-gore-plays-not-my-job-extended-cut [npr.org]
Re: (Score:2)
What's far weirder is that prior to this episode, Bill Clinton aced a quiz on "My Little Pony: Friendship is Magic".
Re: (Score:2)
What's far weirder is that prior to this episode, Bill Clinton aced a quiz on "My Little Pony: Friendship is Magic".
Dunno if it classifies as weird, depending on his reasons for memorizing brony lore. Might have been brilliantly tactical. It is more than a little creepy.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
I thought it was hilarious when he said he invented the internet.
Before a thousand liberals jump on this, the line was "I took the initiative in creating the internet".
Re: (Score:2)
which he did
Re: (Score:2)
ob. joke.. I like my coffee like my men - strong and black.
I like my bourbon like my women -- 13 years old and mixed up with coke.
Re: (Score:2)
Yes.
Re: (Score:2)
ob. joke.. I like my coffee like my men - strong and black.
I like my caffeine the way I like my women: Cold and Yellow.
(I like Mountain Dew/Mello Yello)
Re: (Score:2)
Re: (Score:2)
I like my women like I like my coffee - ground up and in the freezer.
Damn AC, beat me to it!
Re: (Score:2)
Re: (Score:2)
You always liked your coffee like you like your women â" dark, bitter, and they make you all twitchy and irritable and agitated.
Cue the barrage... (Score:4, Funny)
I like my women like I like my sectors, industrial.
Re: (Score:2)
Re: (Score:2)
i sniggered
That's okay. As long as you clean it up before the room-mate arrives.
Re: (Score:2)
Re: (Score:3)
It is definitely a generic frat boy joke generator.
Not sure. It the thing is the I like my women like I like my X...Y are not funny because they say things about women, they're funny because they protray the teller as a gross nerd, creepy, insanely psychopathic, a total sicko, a massive pedo, etc. Listing some of the more popular ones as X|Y
Whisk[e]y | 12 years old and mixed up with coke
Whisky | Never less than 10 years old
Coffee | Ground up and kept in the freezer
Wine | 60 years old and locked in the cella
website! (Score:5, Interesting)
"AI-generated" is an overstatement (Score:5, Informative)
Re: (Score:3)
Exactly. Let us know when the AI generates the formula, instead of just plugging words into it.
Re: (Score:2)
At least it doesn't end every joke with 'Awkward!'.
Re: (Score:2)
Re: (Score:2)
The first one was good; for the others "joke" is an overstatement.
Re: (Score:2)
I showed this a few years ago with an In Soviet Russia joke generator that required no semantic information to generate jokes.
Re: (Score:2)
They wanted to show that ... the AI-joke problem was simpler than previously thought.
If they think this work shows that, they can't have much of a sense of humor.
More seriously, I get the impression that machine learning, and especially unsupervised learning, is the latest hope of the AI community, but I don't think they have shown much reason to believe it will go beyond sophisticated mimicry, with most of the apparent progress being attributable to Moore's law. In this case, they claim that 16% of the generated jokes are considered funny by humans, and I suspect they will find it increasi
This Has Been Done (Score:4, Interesting)
Well, in the movies anyway. Remember the first robot who could NOT get a joke? (Robbie)
And I think the first wise-cracking robot? (Johnny 5 in "Short Circuit")
And then of course there was Data .. with mixed results in reference to humor and jokes.
Re: (Score:2)
"Number 5 not just robot, Number 5, ALIVE!"
Re: (Score:3, Insightful)
What about the computer in "The Moon Is a Harsh Mistress" which was trying to understand humor. One attempt was:
Why is a fish like a laser beam?
Neither on of them can whistle.
It was better at practical jokes, like adding some zeroes on the end of a janitor's paycheck.
Re: (Score:2)
...and Kryten! :-)
And Marvin
"...terrible pain in all the diodes down my left side" cracks me up every time! (c:
Re: (Score:2)
Rimmer: Step up to Red Alert!
Kryten: Sir, are you absolutely sure? It does mean changing the bulb.
So... (Score:2)
Women (Score:5, Funny)
I like my women like I like my AI joke generator. Inaccessible to most of the interested geeks.
Data from ST:TNG (Score:2)
SomethingAwful (Score:2)
That's what she said (Score:5, Interesting)
Re: (Score:2)
I like my women like I like my gas ... natural (misogynistic) ... buried (misandristic)
I like my men like I like my acorns
I like my boys like I like my sectors bad (???)
I like my men like I like my monoxide - odourless (misandristic)
I like my men like I like my court superior (misogynistic)
I would say, given the information I have here, that the computer isn't really biased one way or the other, it hates everyone. Huzzah! Now we have a digital misanthropic comedian.
Re: (Score:2)
I like my men like I like my acorns ... buried (misandristic)
I'd argue this one is misogynistic, if you interpret it as a woman talking about being a grave-robber [urbandictionary.com].
Re: (Score:2)
Yeah, looks like the Telegraph is just trying to drum up pageviews.
I'm guessing they algorithm used is pretty simple, text mine for pairs of nouns that share a common adjective and you have your joke.
It wouldn't be surprising if the funniest pairings were risque since breaking social norms is one of the basis for humour, I'm actually surprised they couldn't find actual misogynist examples. Depending on the telling even this one "I like my women like I like my gas ... natural (misogynistic)" is potentially n
Really like to see someone implement this (Score:3)
My hound hath no nose (Score:2)
Re: (Score:2)
Joke warfare was banned. Surely the UN will step-in.
The Essence of Humor (Score:5, Insightful)
Usually people mix up humor and powerful humor. So they think of all the ingredients that make it work. The best example of humor is then the one that makes you laugh more.
But here's another angle: Just think of humor as having a humor part and a booster that makes you laugh more. The humor part is just the perception switch. It can be pretty mild. But add the naughtiness, the meanness , the embarassment and they provide a boost to the humor.
Taken that way, the AI examples in the topic article are really touching the essence of humor.
Re: (Score:2)
The essence of humor is surprise. They are getting surprise by looking for words that have different meanings in different contexts and using a canned phrasing to bring two disparate contexts together only on the very last word of the sentence - which bring the surprise. The boost you speak of is possibly there by combining a charged topic like "relationships" with something very boring like software or "source".
Boo! (Score:2)
Well, surprise isn't the same as a perception switch, although there's overlap. Because I describe humor as a perception switch I'm saying it's the same mechanism as insight. Suddenly understanding something. Not that I came up with that myself.
Re: (Score:2)
The essence of humo[u]r is surprise.
Surprise and fear.
Re: (Score:2)
Surprise and fear.
And now that it's computerized, a ruthless efficiency is within our reach!
Re: (Score:2)
Surprise and fear
... and ruthless efficiency
I like my noun like I like my noun, (Score:2)
In Soviet Russia... (Score:2)
...Turing Test passes YOU!
Context is important (Score:3)
You need Dr. Strangelove to walk into a coffee shop, and for the barista to ask him how he likes his coffee. Then MAYBE it's funny. Furthermore, the deliver and timing matters. You can deliver that line and kill or die. Finally, the person who sees this might not get it, or they might get it and just not think it's funny. Yeah, yeah, Dr. Strangelove likes the cold war. Not funny... to that guy; but maybe funny to you.
Sure - Siri... (Score:2)
Context Error on line 1: Expected humor. (Score:2)
I like my machines like I like myself, Intelligent.
Mapping a common property between two different subjects literally isn't remarkable in of itself. A comedian invents far more jokes than they tell. You see, the trick isn't in coming up with jokes, it's knowing when they're funny enough to repeat.
Humor is an exploit of laughter as social bonding (Score:3)
In Mind Wide Open [amazon.com] Steven Johnson points out that "Laughing is not an instinctive physical response to humor, the way a flinch responds to pain or a shiver to cold. It's an instinctive form of social bonding that humor is crafted to exploit."
Think about how often you laugh at references, the more obscure the better. You're sharing a bond with the person making that reference—and once you start looking for that, it becomes increasingly obvious (at least it did for me).
That's probably why "I like my X like my Y, Z" style jokes are funny—they make us think, "Wow, you and I both see that X and Y have that relationship, possibly based on abusing a synonym, which doesn't immediately spring to mind when you think of them."
The more I think about humor as an exploit of laughter as social bonding behavior, the more I notice it. And the more I notice people laughing when things aren't funny, but when it's appropriate to reconfirm a social bond (like when someone does something embarrassing that might take them out of the social norm, and the people around them laugh to reassure them that the social bond has not been damaged... much).
This is where I would make a joke about how geeks are not good at social bonding, but I'm too much of a geek to relate to such things.
Re: (Score:2)
Which is why I hate TV shows with laugh tracks; particularly the ones that go off on every pause, even for non-jokes.
Re: (Score:2)
Re: (Score:2)
If laughter is a social bonding behavior, why do people laugh at something they are reading when they are completely alone?
One's never alone with a good book...
(i.e. at the very least you're engaging socially in some sense with the author, and likely with the characters in the story as well)
Re: (Score:2)
What is this? (Score:2)
Funny AI? (Score:2)
Here I am, brain the size of a planet, and they ask me to make puns. Call that job satisfaction, 'cause I don't.
Schubert's 8th (Score:5, Interesting)
I like my jokes like I like my symphonies
-
Re: (Score:2)
That's not really automatic is it? (Score:2)
176 Comments And No Asimov Reverence? (Score:2)
This story seems inspired by Asimov's "Jokester", in which a humor "Grand Master" is attempting to find the source of humor by feeding Multivac a curated set of jokes. I won't spoil the ending, but let's just say the mice need a new maze at the end.
I looked at TFA (Score:2)
Re:Ok, now let me try... (Score:4, Funny)
...I like my computer generated joke examples like I like my MSDN how-to articles...terrible?
I like my computer generated jokes like I like my computer joke generator errors...
Re: (Score:3)
I like my AI like I like my zombies, mancery.
I like my AI like I like my - INSERT DISK 2 TO CONTINUE
Re: (Score:2)
Just like at the movie theater!
Oops, wrong reference...
Re: (Score:2)
I've had a copy of Garfield's Book of Insults, Put-Downs, and Slams [amazon.com] since it was published in 1994, and I have to say, some of the best burns I've ever heard were contained therein.
No, seriously.
Re: (Score:2)
were there any actual generated jokes in the TFA?whoever generated the pattern blabla like bla, bla and put in the data generated the jokes and he knew they would come out so no AI. the one's in the submission could have been "generated" with qbasic and a txt full of suitable words.
Re: (Score:2)
I always wanted to be like Al when I grew up. Spoiler alert: I failed miserably.
Re: (Score:2)
I always wanted to be like Al when I grew up. Spoiler alert: I failed miserably.
The beard didn't fill in, did it?
Re: (Score:2)